recipes/zephyr-7b-gemma/sft/config_full.yaml

# Model arguments
model_name_or_path: google/gemma-7b
model_revision: main
tokenizer_name_or_path: philschmid/gemma-tokenizer-chatml # Custom tokenizer with <|im_start|> and <|im_end|> tokens
torch_dtype: bfloat16
attn_implementation: flash_attention_2

# Data training arguments
dataset_mixer:
  HuggingFaceH4/deita-10k-v0-sft: 1.0
dataset_splits:
- train_sft
- test_sft
preprocessing_num_workers: 12

# SFT trainer config
bf16: true
dataset_kwargs:
  add_special_tokens: false  # We already wrap <bos> and <eos> in the chat template
  append_concat_token: false # No need to add <eos> across samples
do_eval: true
eval_strategy: epoch
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
hub_model_id: zephyr-7b-gemma-sft
hub_strategy: every_save
learning_rate: 2.0e-05
log_level: info
logging_steps: 5
logging_strategy: steps
lr_scheduler_type: cosine
max_seq_length: 2048
max_steps: -1
num_train_epochs: 3
output_dir: data/zephyr-7b-gemma-sft
overwrite_output_dir: true
per_device_eval_batch_size: 4
per_device_train_batch_size: 4
push_to_hub: true
remove_unused_columns: true
report_to:
- tensorboard
- wandb
save_strategy: "no"
seed: 42
warmup_ratio: 0.1